Collaborative Control Method of Transit Signal Priority Based on Cooperative Game and Reinforcement Learning

Transit Signal Priority (TSP) control plays a critical role in enhancing the efficiency and safety of transportation systems, particularly in Bus Rapid Transit (BRT) and emergency scenarios. Traditional TSP methods typically operate on fixed-time signal schedules, adjusting traffic signals based on predefined timetables. In this study, we introduce a novel eight-phase TSP method tailored for BRT systems, aimed at optimizing stability for private vehicles while ensuring reliable bus service. Our approach integrates cooperative game theory with reinforcement learning in a joint decision-making framework that prioritizes both buses and private vehicles under specific operational constraints. This method not only adheres to the fairness principles inherent in cooperative game theory but also leverages the adaptive capabilities of Q-learning to dynamically refine decision-making processes. The proposed system promises to significantly improve the responsiveness and effectiveness of traffic signal control in urban settings.